Di Su
Research Subjects
Di Su has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Cheng Zhang
Beijing Institute of Technology
2 shared publications - Fan Liu
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, USA
1 shared publication G H Rao
School of Materials Science and Engineering & Guangxi Key Laboratory of Information Materials, Guilin University of Electronic Technology, Guilin 541004, People's Republic of China
1 shared publicationH Y Zhou
1 shared publication- Hui Jin
State Key Laboratory of Multiphase Flow in Power Engineering
1 shared publication Ji-Qiong Liu
School of Materials Science and Engineering, Shanghai University, Shanghai, 200444, China
1 shared publication
Latest Publications
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
An Orthogonal Fusion of Local and Global Features for Drone-based Geo-localization
Drone-based geo-localization is an image retrieval task which is the foundation of many drone-based multimedia applications, such as object detection, drone navigation and mapping. It is challenging due to the large visual appearance changes caused by viewpoint variation and time misalignment. Existing methods primarily focus on global representation embedding while disregarding the local features. We propose a CNN-based model containing a global and a local branch to extract features in these two perspectives and then features are subsequently aggregated by orthogonal fusion. We achieve competitive results on University-1652/160k datasets among the ViT-based state-of-the-art models. Experimental and qualitative results that validate the effectiveness of our solution are also shown.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessAn Orthogonal Fusion of Local and Global Features for Drone-based Geo-localization
Drone-based geo-localization is an image retrieval task which is the foundation of many drone-based multimedia applications, such as object detection, drone navigation and mapping. It is challenging due to the large visual appearance changes caused by viewpoint variation and time misalignment. Existing methods primarily focus on global representation embedding while disregarding the local features. We propose a CNN-based model containing a global and a local branch to extract features in these two perspectives and then features are subsequently aggregated by orthogonal fusion. We achieve competitive results on University-1652/160k datasets among the ViT-based state-of-the-art models. Experimental and qualitative results that validate the effectiveness of our solution are also shown.
- 20 March 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (20) , 31557-31573
SR-net: satellite relative pose estimation network for a noncooperative target via RGB images
- 20 March 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (20) , 31557-31573
SR-net: satellite relative pose estimation network for a noncooperative target via RGB images
- Open Access
- 1 October 2020
- Published by IOP Publishing in Materials Research Express
- Vol. 7 (10) , 106513
Solidification microstructure and phase transition of La-Nd-Fe alloys
The solidification microstructure and phase transition of ten La-Nd-Fe alloys were studied experimentally by scanning electron microscopy (SEM) with energy dispersive x-ray spectroscopy (EDS) and differential thermal analysis (DTA). Phase compositions and phase transition temperatures of La-Nd-Fe alloys were measured and the formed phases were identified. The solidification behavior of La-Nd-Fe alloys was analyzed based on the experimental results of both solidification microstructure and phase transitions with the reported Nd-Fe, La-Fe and La-Nd sub-binary phase diagrams. The results indicated that the solidification processes of all La-Nd-Fe alloys begin with the precipitation of primary phase fcc(γ-Fe) and then follow by the formation of bcc(α-Fe) and/or Fe17Nd2 phases through different peritectic reactions. The solidification microstructure of three Fe65La29Nd6, Fe65La25Nd10 and Fe65La22Nd13 alloys presents three-phase microstructure with bcc(α-Fe), Fe17Nd2 and fcc(La,Nd) phases, while that of three Fe65La19Nd16, Fe65La9Nd26 and Fe65La15.5Nd19.5 alloys shows three-phase microstructure with bcc(α-Fe), Fe17Nd2 and dhcp(La,Nd) phases. The two-phase micorstructure with Fe17Nd2 and dhcp(La,Nd) ohases was formed in the solidification microstructure of four Fe65La12Nd23, Fe65La6.5Nd28.5, Fe65La4Nd31 and Fe65La1.5Nd33.5 alloys. Moreover, no stable ternary intermetallic compound was found in the present experiments. The solidification microstructure and phase transition of La-Nd-Fe alloys would provide a basis for the design of La-Nd-Fe-B magnetic alloys.
- 1 October 2020
- Published by IOP Publishing in Materials Research Express
- Vol. 7 (10) , 106513
Open AccessSolidification microstructure and phase transition of La-Nd-Fe alloys
The solidification microstructure and phase transition of ten La-Nd-Fe alloys were studied experimentally by scanning electron microscopy (SEM) with energy dispersive x-ray spectroscopy (EDS) and differential thermal analysis (DTA). Phase compositions and phase transition temperatures of La-Nd-Fe alloys were measured and the formed phases were identified. The solidification behavior of La-Nd-Fe alloys was analyzed based on the experimental results of both solidification microstructure and phase transitions with the reported Nd-Fe, La-Fe and La-Nd sub-binary phase diagrams. The results indicated that the solidification processes of all La-Nd-Fe alloys begin with the precipitation of primary phase fcc(γ-Fe) and then follow by the formation of bcc(α-Fe) and/or Fe17Nd2 phases through different peritectic reactions. The solidification microstructure of three Fe65La29Nd6, Fe65La25Nd10 and Fe65La22Nd13 alloys presents three-phase microstructure with bcc(α-Fe), Fe17Nd2 and fcc(La,Nd) phases, while that of three Fe65La19Nd16, Fe65La9Nd26 and Fe65La15.5Nd19.5 alloys shows three-phase microstructure with bcc(α-Fe), Fe17Nd2 and dhcp(La,Nd) phases. The two-phase micorstructure with Fe17Nd2 and dhcp(La,Nd) ohases was formed in the solidification microstructure of four Fe65La12Nd23, Fe65La6.5Nd28.5, Fe65La4Nd31 and Fe65La1.5Nd33.5 alloys. Moreover, no stable ternary intermetallic compound was found in the present experiments. The solidification microstructure and phase transition of La-Nd-Fe alloys would provide a basis for the design of La-Nd-Fe-B magnetic alloys.
- Open Access
- 1 January 2015
- Published by Atlantis Press SARL
Establishment of the Elastic Property Database of Fe-base Alloys
- 1 January 2015
- Published by Atlantis Press SARL
Open AccessEstablishment of the Elastic Property Database of Fe-base Alloys